Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units
Abstract
In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE) compression algorithm. Compared to using words as modeling units, using characters or subword units does not suffer from the out-of-vocabulary (OOV) problem. Furthermore, using subword units further offers a capability in modeling longer context than using characters. We evaluate different systems over the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attention system obtains 6.8% word error rate (WER) on the test_clean subset without any dictionary or external language model. This represents a significant improvement (a 12.8% WER relative reduction) over the character-based hybrid CTC-Attention system.
- Publication:
-
arXiv e-prints
- Pub Date:
- July 2018
- DOI:
- 10.48550/arXiv.1807.04978
- arXiv:
- arXiv:1807.04978
- Bibcode:
- 2018arXiv180704978X
- Keywords:
-
- Electrical Engineering and Systems Science - Audio and Speech Processing;
- Computer Science - Computation and Language;
- Computer Science - Sound
- E-Print:
- accepted by ISCSLP 2018